fix：移除了部分token限制

src/chat/focus_chat/expressors/default_expressor.py

@@ -77,7 +77,6 @@ class DefaultExpressor:
         # TODO: API-Adapter修改标记
         self.express_model = LLMRequest(
             model=global_config.model.replyer_1,
-            max_tokens=256,
             request_type="focus.expressor",
         )
         self.heart_fc_sender = HeartFCSender()

src/chat/focus_chat/expressors/exprssion_learner.py

@@ -70,7 +70,6 @@ class ExpressionLearner:
         self.express_learn_model: LLMRequest = LLMRequest(
             model=global_config.model.replyer_1,
             temperature=0.1,
-            max_tokens=256,
             request_type="expressor.learner",
         )
 

src/chat/focus_chat/info_processors/chattinginfo_processor.py

@@ -31,7 +31,6 @@ class ChattingInfoProcessor(BaseProcessor):
         self.model_summary = LLMRequest(
             model=global_config.model.utils_small,
             temperature=0.7,
-            max_tokens=300,
             request_type="focus.observation.chat",
         )
 

src/chat/focus_chat/info_processors/mind_processor.py

@@ -69,7 +69,6 @@ class MindProcessor(BaseProcessor):
 
         self.llm_model = LLMRequest(
             model=global_config.model.planner,
-            max_tokens=800,
             request_type="focus.processor.chat_mind",
         )
 

src/chat/focus_chat/info_processors/relationship_processor.py

@@ -37,7 +37,7 @@ def init_prompt():
 你不同程度上认识群聊里的人，你可以根据聊天记录，回忆起有关他们的信息，帮助你参与聊天
 1.你需要提供用户名，以及你想要提取的信息名称类型来进行调取
 2.你也可以完全不输出任何信息
-3.如果短期内已经回忆过某个人的信息，请不要重复调取，除非你忘记了
+3.阅读调取记录，如果已经回忆过某个人的信息，请不要重复调取，除非你忘记了
 
 请以json格式输出，例如：
 
@@ -95,7 +95,7 @@ class RelationshipProcessor(BaseProcessor):
         self.llm_model = LLMRequest(
             model=global_config.model.relation,
             max_tokens=800,
-            request_type="relation",
+            request_type="focus.relationship",
         )
 
         name = chat_manager.get_stream_name(self.subheartflow_id)
@@ -206,10 +206,10 @@ class RelationshipProcessor(BaseProcessor):
         )
         
         try:
-            logger.info(f"{self.log_prefix} 人物信息prompt: \n{prompt}\n")
+            # logger.info(f"{self.log_prefix} 人物信息prompt: \n{prompt}\n")
             content, _ = await self.llm_model.generate_response_async(prompt=prompt)
             if content:
-                print(f"content: {content}")
+                # print(f"content: {content}")
                 content_json = json.loads(repair_json(content))
 
                 for person_name, info_type in content_json.items():
@@ -347,7 +347,7 @@ class RelationshipProcessor(BaseProcessor):
         try:
             content, _ = await self.llm_model.generate_response_async(prompt=prompt)
             
-            logger.info(f"{self.log_prefix} fetch_person_info prompt: \n{prompt}\n")
+            # logger.info(f"{self.log_prefix} fetch_person_info prompt: \n{prompt}\n")
             logger.info(f"{self.log_prefix} fetch_person_info 结果: {content}")
             
             if content:

src/chat/focus_chat/memory_activator.py

@@ -72,7 +72,6 @@ class MemoryActivator:
         self.summary_model = LLMRequest(
             model=global_config.model.memory_summary,
             temperature=0.7,
-            max_tokens=50,
             request_type="focus.memory_activator",
         )
         self.running_memory = []

src/chat/focus_chat/planners/actions/plugin_action.py

@@ -348,7 +348,6 @@ class PluginAction(BaseAction):
         self,
         prompt: str,
         model_config: Dict[str, Any],
-        max_tokens: int = 2000,
         request_type: str = "plugin.generate",
         **kwargs
     ) -> Tuple[bool, str]:
@@ -372,7 +371,6 @@ class PluginAction(BaseAction):
             
             llm_request = LLMRequest(
                 model=model_config,
-                max_tokens=max_tokens,
                 request_type=request_type,
                 **kwargs
             )

src/chat/focus_chat/replyer/default_replyer.py

@@ -88,8 +88,7 @@ class DefaultReplyer:
         # TODO: API-Adapter修改标记
         self.express_model = LLMRequest(
             model=global_config.model.replyer_1,
-            max_tokens=256,
+            request_type="focus.replyer",
-            request_type="focus.expressor",
         )
         self.heart_fc_sender = HeartFCSender()
 

src/chat/focus_chat/working_memory/memory_manager.py

@@ -35,7 +35,6 @@ class MemoryManager:
         self.llm_summarizer = LLMRequest(
             model=global_config.model.focus_working_memory,
             temperature=0.3,
-            max_tokens=512,
             request_type="focus.processor.working_memory",
         )
 

src/chat/normal_chat/normal_chat_generator.py

@@ -19,19 +19,15 @@ class NormalChatGenerator:
         # TODO: API-Adapter修改标记
         self.model_reasoning = LLMRequest(
             model=global_config.model.replyer_1,
-            # temperature=0.7,
-            max_tokens=3000,
             request_type="normal.chat_1",
         )
         self.model_normal = LLMRequest(
             model=global_config.model.replyer_2,
-            # temperature=global_config.model.replyer_2["temp"],
-            max_tokens=256,
             request_type="normal.chat_2",
         )
 
         self.model_sum = LLMRequest(
-            model=global_config.model.memory_summary, temperature=0.7, max_tokens=3000, request_type="relation"
+            model=global_config.model.memory_summary, temperature=0.7, request_type="relation"
         )
         self.current_model_type = "r1"  # 默认使用 R1
         self.current_model_name = "unknown model"

src/experimental/PFC/action_planner.py

@@ -110,7 +110,6 @@ class ActionPlanner:
         self.llm = LLMRequest(
             model=global_config.llm_PFC_action_planner,
             temperature=global_config.llm_PFC_action_planner["temp"],
-            max_tokens=1500,
             request_type="action_planning",
         )
         self.personality_info = individuality.get_prompt(x_person=2, level=3)

src/experimental/PFC/reply_generator.py

@@ -89,7 +89,6 @@ class ReplyGenerator:
         self.llm = LLMRequest(
             model=global_config.llm_PFC_chat,
             temperature=global_config.llm_PFC_chat["temp"],
-            max_tokens=300,
             request_type="reply_generation",
         )
         self.personality_info = individuality.get_prompt(x_person=2, level=3)

src/person_info/person_info.py

@@ -56,7 +56,6 @@ class PersonInfoManager:
         # TODO: API-Adapter修改标记
         self.qv_name_llm = LLMRequest(
             model=global_config.model.utils,
-            max_tokens=256,
             request_type="relation.qv_name",
         )
         try:

tests/test_relationship_processor.py

@@ -128,7 +128,6 @@ class RelationshipProcessor:
 
         self.llm_model = LLMRequest(
             model=global_config.model.relation,
-            max_tokens=800,
             request_type="relation",
         )